@inproceedings{Turpault2019_DCASE,
    Author = "Turpault, Nicolas and Serizel, Romain and Parag Shah, Ankit and Salamon, Justin",
    title = "{Sound event detection in domestic environments with weakly labeled data and soundscape synthesis}",
    booktitle = "{Workshop on Detection and Classification of Acoustic Scenes and Events}",
    address = "New York City, United States",
    year = "2019",
    month = "October",
    keywords = "Sound event detection ; Weakly labeled data ; Semi-supervised learning ; Synthetic data",
    abstract = "This paper presents Task 4 of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2019 challenge and provides a first analysis of the challenge results. The task is a followup to Task 4 of DCASE 2018, and involves training systems for large-scale detection of sound events using a combination of weakly labeled data, i.e. training labels without time boundaries, and strongly-labeled synthesized data. The paper introduces Domestic Environment Sound Event Detection (DESED) dataset mixing a part of last year dataset and an additional synthetic, strongly labeled, dataset provided this year that we’ll describe more in detail. We also report the performance of the submitted systems on the official evaluation (test) and development sets as well as several additional datasets. The best systems from this year outperform last year’s winning system by about 10\% points in terms of F-measure.",
    hal_id = "hal-02160855",
    hal_version = "v2",
    url = "https://hal.inria.fr/hal-02160855"
}

@inproceedings{Serizel2020_ICASSP,
    Author = "Serizel, Romain and Turpault, Nicolas and Shah, Ankit and Salamon, Justin",
    title = "{Sound event detection in synthetic domestic environments}",
    booktitle = "{ICASSP 2020 - 45th International Conference on Acoustics, Speech, and Signal Processing}",
    address = "Barcelona, Spain",
    year = "2020",
    keywords = "semi-supervised learning ; weakly labeled data ; synthetic data ; Sound event detection ; Index Terms-Sound event detection",
    abstract = "This paper presents Task 4 of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2019 challenge and provides a first analysis of the challenge results. The task is a followup to Task 4 of DCASE 2018, and involves training systems for large-scale detection of sound events using a combination of weakly labeled data, i.e. training labels without time boundaries, and strongly-labeled synthesized data. The paper introduces Domestic Environment Sound Event Detection (DESED) dataset mixing a part of last year dataset and an additional synthetic, strongly labeled, dataset provided this year that we’ll describe more in detail. We also report the performance of the submitted systems on the official evaluation (test) and development sets as well as several additional datasets. The best systems from this year outperform last year’s winning system by about 10\% points in terms of F-measure.",
    hal_id = "hal-02355573",
    hal_version = "v2",
    url = "https://hal.inria.fr/hal-02355573"
}

@inproceedings{fonseca2020fsd50k,
    author = "Fonseca, Eduardo and Favory, Xavier and Pons, Jordi and Font, Frederic and Serra, Xavier",
    title = "{FSD50K}: an Open Dataset of Human-Labeled Sound Events",
    year = "2020",
    booktitle = "arXiv:2010.00475",
    abstract = "Most existing datasets for sound event recognition (SER) are relatively small and/or domain-specific, with the exception of AudioSet, based on a massive amount of audio tracks from YouTube videos and encompassing over 500 classes of everyday sounds. However, AudioSet is not an open dataset---its release consists of pre-computed audio features (instead of waveforms), which limits the adoption of some SER methods. Downloading the original audio tracks is also problematic due to constituent YouTube videos gradually disappearing and usage rights issues, which casts doubts over the suitability of this resource for systems' benchmarking. To provide an alternative benchmark dataset and thus foster SER research, we introduce FSD50K, an open dataset containing over 51k audio clips totalling over 100h of audio manually labeled using 200 classes drawn from the AudioSet Ontology. The audio clips are licensed under Creative Commons licenses, making the dataset freely distributable (including waveforms). We provide a detailed description of the FSD50K creation process, tailored to the particularities of Freesound data, including challenges encountered and solutions adopted. We include a comprehensive dataset characterization along with discussion of limitations and key factors to allow its audio-informed usage. Finally, we conduct sound event classification experiments to provide baseline systems as well as insight on the main factors to consider when splitting Freesound audio data for SER. Our goal is to develop a dataset to be widely adopted by the community as a new open benchmark for SER research."
}

@inproceedings{font2013freesound,
    author = "Font, Frederic and Roma, Gerard and Serra, Xavier",
    title = "Freesound technical demo",
    booktitle = "Proceedings of the 21st ACM international conference on Multimedia",
    pages = "411--412",
    year = "2013",
    organization = "ACM",
    abstract = "Freesound is an online collaborative sound database where people with diverse interests share recorded sound samples under Creative Commons licenses. It was started in 2005 and it is being maintained to support diverse research projects and as a service to the overall research and artistic community. In this demo we want to introduce Freesound to the multimedia community and show its potential as a research resource. We begin by describing some general aspects of Freesound, its architecture and functionalities, and then explain potential usages that this framework has for research applications."
}

@inproceedings{Wisdom_InPrep2020,
    Author = "Wisdom, Scott and Erdogan, Hakan and Ellis, Daniel P. W. and Serizel, Romain and Turpault, Nicolas and Fonseca, Eduardo and Salamon, Justin and Seetharaman, Prem and Hershey, John R.",
    title = "What's All the FUSS About Free Universal Sound Separation Data?",
    year = "2020",
    booktitle = "in preparation"
}

@inproceedings{Dekkers2017,
    Author = "Dekkers, Gert and Lauwereins, Steven and Thoen, Bart and Adhana, Mulu Weldegebreal and Brouckxon, Henk and van Waterschoot, Toon and Vanrumste, Bart and Verhelst, Marian and Karsmakers, Peter",
    title = "The {SINS} Database for Detection of Daily Activities in a Home Environment Using an Acoustic Sensor Network",
    booktitle = "Proceedings of the Detection and Classification of Acoustic Scenes and Events 2017 Workshop (DCASE2017)",
    year = "2017",
    month = "November",
    pages = "32--36",
    abstract = "There is a rising interest in monitoring and improving human wellbeing at home using different types of sensors including microphones. In the context of Ambient Assisted Living (AAL) persons are monitored, e.g. to support patients with a chronic illness and older persons, by tracking their activities being performed at home. When considering an acoustic sensing modality, a performed activity can be seen as an acoustic scene. Recently, acoustic detection and classification of scenes and events has gained interest in the scientific community and led to numerous public databases for a wide range of applications. However, no public databases exist which a) focus on daily activities in a home environment, b) contain activities being performed in a spontaneous manner, c) make use of an acoustic sensor network, and d) are recorded as a continuous stream. In this paper we introduce a database recorded in one living home, over a period of one week. The recording setup is an acoustic sensor network containing thirteen sensor nodes, with four low-cost microphones each, distributed over five rooms. Annotation is available on an activity level. In this paper we present the recording and annotation procedure, the database content and a discussion on a baseline detection benchmark. The baseline consists of Mel-Frequency Cepstral Coefficients, Support Vector Machine and a majority vote late-fusion scheme. The database is publicly released to provide a common ground for future research.",
    keywords = "Database, Acoustic Scene Classification, Acoustic Event Detection, Acoustic Sensor Networks"
}

@inproceedings{Mesaros2016_EUSIPCO,
    author = "Mesaros, Annamaria and Heittola, Toni and Virtanen, Tuomas",
    title = "{TUT} Database for Acoustic Scene Classification and Sound Event Detection",
    abstract = "We introduce TUT Acoustic Scenes 2016 database for environmental sound research, consisting ofbinaural recordings from 15 different acoustic environments. A subset of this database, called TUT Sound Events 2016, contains annotations for individual sound events, specifically created for sound event detection. TUT Sound Events 2016 consists of residential area and home environments, and is manually annotated to mark onset, offset and label of sound events. In this paper we present the recording and annotation procedure, the database content, a recommended cross-validation setup and performance of supervised acoustic scene classification system and event detection baseline system using mel frequency cepstral coefficients and Gaussian mixture models. The database is publicly released to provide support for algorithm development and common ground for comparison of different techniques.",
    year = "2016",
    address = "Budapest, Hungary",
    booktitle = "24th European Signal Processing Conference 2016 (EUSIPCO 2016)"
}

@inproceedings{Salamon2017_WASPAA,
    Author = "Salamon, J. and MacConnell, D. and Cartwright, M. and Li, P. and Bello, J. P.",
    address = "New Paltz, NY, USA",
    booktitle = "IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)",
    month = "Oct.",
    pages = "344--348",
    title = "Scaper: A Library for Soundscape Synthesis and Augmentation",
    year = "2017"
}

@inproceedings{fonseca2020fsd50k,
    author = "Fonseca, Eduardo and Favory, Xavier and Pons, Jordi and Font, Frederic and Serra, Xavier",
    title = "{FSD50K}: an Open Dataset of Human-Labeled Sound Events",
    year = "2020",
    booktitle = "arXiv:2010.00475",
    abstract = "Most existing datasets for sound event recognition (SER) are relatively small and/or domain-specific, with the exception of AudioSet, based on a massive amount of audio tracks from YouTube videos and encompassing over 500 classes of everyday sounds. However, AudioSet is not an open dataset---its release consists of pre-computed audio features (instead of waveforms), which limits the adoption of some SER methods. Downloading the original audio tracks is also problematic due to constituent YouTube videos gradually disappearing and usage rights issues, which casts doubts over the suitability of this resource for systems' benchmarking. To provide an alternative benchmark dataset and thus foster SER research, we introduce FSD50K, an open dataset containing over 51k audio clips totalling over 100h of audio manually labeled using 200 classes drawn from the AudioSet Ontology. The audio clips are licensed under Creative Commons licenses, making the dataset freely distributable (including waveforms). We provide a detailed description of the FSD50K creation process, tailored to the particularities of Freesound data, including challenges encountered and solutions adopted. We include a comprehensive dataset characterization along with discussion of limitations and key factors to allow its audio-informed usage. Finally, we conduct sound event classification experiments to provide baseline systems as well as insight on the main factors to consider when splitting Freesound audio data for SER. Our goal is to develop a dataset to be widely adopted by the community as a new open benchmark for SER research."
}

@inproceedings{font2013freesound,
    author = "Font, Frederic and Roma, Gerard and Serra, Xavier",
    title = "Freesound technical demo",
    booktitle = "Proceedings of the 21st ACM international conference on Multimedia",
    pages = "411--412",
    year = "2013",
    organization = "ACM",
    abstract = "Freesound is an online collaborative sound database where people with diverse interests share recorded sound samples under Creative Commons licenses. It was started in 2005 and it is being maintained to support diverse research projects and as a service to the overall research and artistic community. In this demo we want to introduce Freesound to the multimedia community and show its potential as a research resource. We begin by describing some general aspects of Freesound, its architecture and functionalities, and then explain potential usages that this framework has for research applications."
}

@article{Mesaros2016_MDPI,
    Author = "Mesaros, Annamaria and Heittola, Toni and Virtanen, Tuomas",
    title = "Metrics for Polyphonic Sound Event Detection",
    journal = "Applied Sciences",
    year = "2016",
    number = "6",
    pages = "162",
    volume = "6",
    abstract = "This paper presents and discusses various metrics proposed for evaluation of polyphonic sound event detection systems used in realistic situations where there are typically multiple sound sources active simultaneously. The system output in this case contains overlapping events, marked as multiple sounds detected as being active at the same time. The polyphonic system output requires a suitable procedure for evaluation against a reference. Metrics from neighboring fields such as speech recognition and speaker diarization can be used, but they need to be partially redefined to deal with the overlapping events. We present a review of the most common metrics in the field and the way they are adapted and interpreted in the polyphonic case. We discuss segment-based and event-based definitions of each metric and explain the consequences of instance-based and class-based averaging using a case study. In parallel, we provide a toolbox containing implementations of presented metrics.",
    doi = "10.3390/app6060162",
    issn = "2076-3417",
    url = "http://www.mdpi.com/2076-3417/6/6/162"
}

@article{Bilen2020,
    author = "Bilen, Cagdas and Ferroni, Giacomo and Tuveri, Francesco and Azcarreta, Juan and Krstulovic, Sacha",
    title = "A Framework for the Robust Evaluation of Sound Event Detection",
    journal = "arXiv preprint arXiv:1910.08440",
    year = "2019",
    url = "https://arxiv.org/abs/1910.08440"
}

@unpublished{Turpault2020a,
    AUTHOR = "Turpault, Nicolas and Serizel, Romain",
    title = "Training Sound Event Detection On A Heterogeneous Dataset",
    note = "working paper or preprint",
    institution = "Universit{\'e} de Lorraine, CNRS, Inria, Loria, France",
    year = "2020",
    abstract = "Training a sound event detection algorithm on a heterogeneous dataset including both recorded and synthetic soundscapes that can have various labeling granularity is a non-trivial task that can lead to systems requiring several technical choices. These technical choices are often passed from one system to another without being questioned. We propose to perform a detailed analysis of DCASE 2020 task 4 sound event detection baseline with regards to several aspects such as the type of data used for training, the parameters of the mean-teacher or the transformations applied while generating the synthetic soundscapes. Some of the parameters that are usually used as default to replicate other approaches are shown to be sub-optimal."
}

@techreport{Delphin-Poulat2019,
    Author = "Delphin-Poulat, Lionel and Plapous, Cyril",
    title = "MEAN TEACHER WITH DATA AUGMENTATION FOR DCASE 2019 TASK 4",
    institution = "Orange Labs Lannion, France",
    year = "2019",
    month = "June",
    abstract = "In this paper, we present our neural network for the DCASE 2019 challenge’s Task 4 (Sound event detection in domestic environments) [1]. The goal of the task is to evaluate systems for the detection of sound events using real data either weakly labeled or unlabeled and simulated data that is strongly labeled. We propose a mean-teacher model with convolutional neural network (CNN) and recurrent neural network (RNN) together with data augmentation and a median window tuned for each class based on prior knowledge."
}

@inproceedings{tarvainen2017mean,
    author = "Tarvainen, Antti and Valpola, Harri",
    title = "Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results",
    booktitle = "Advances in neural information processing systems",
    pages = "1195--1204",
    year = "2017",
    abstract = "The recently proposed Temporal Ensembling has achieved state-of-the-art results in several semi-supervised learning benchmarks. It maintains an exponential moving average of label predictions on each training example, and penalizes predictions that are inconsistent with this target. However, because the targets change only once per epoch, Temporal Ensembling becomes unwieldy when learning large datasets. To overcome this problem, we propose Mean Teacher, a method that averages model weights instead of label predictions. As an additional benefit, Mean Teacher improves test accuracy and enables training with fewer labels than Temporal Ensembling. Without changing the network architecture, Mean Teacher achieves an error rate of 4.35\% on SVHN with 250 labels, outperforming Temporal Ensembling trained with 1000 labels. We also show that a good network architecture is crucial to performance. Combining Mean Teacher and Residual Networks, we improve the state of the art on CIFAR-10 with 4000 labels from 10.55\% to 6.28\%, and on ImageNet 2012 with 10\% of the labels from 35.24\% to 9.11\%."
}

@inproceedings{Kavalerov_WASPAA2019,
    Author = "Kavalerov, Ilya and Wisdom, Scott and Erdogan, Hakan and Patton, Brian and Wilson, Kevin and {Le Roux}, Jonathan and Hershey, John R.",
    title = "Universal Sound Separation",
    year = "2019",
    booktitle = "{IEEE} Workshop on Applications of Signal Processing to Audio and Acoustics ({WASPAA})",
    month = "October",
    pages = "175--179",
    url = "https://arxiv.org/abs/1905.03330"
}

@inproceedings{Tzinis_ICASSP2020,
    Author = "Tzinis, Efthymios and Wisdom, Scott and Hershey, John R. and Jansen, Aren and Ellis, Daniel P. W.",
    title = "Improving Universal Sound Separation Using Sound Classification",
    year = "2020",
    booktitle = "{IEEE} International Conference on Acoustics, Speech, and Signal Processing ({ICASSP})",
    month = "May",
    url = "https://arxiv.org/abs/1911.07951"
}

@inproceedings{Wisdom_ICASSP2019,
    author = "Wisdom, Scott and Hershey, John R and Wilson, Kevin and Thorpe, Jeremy and Chinen, Michael and Patton, Brian and Saurous, Rif A",
    title = "Differentiable consistency constraints for improved deep speech enhancement",
    booktitle = "ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",
    pages = "900--904",
    year = "2019",
    organization = "IEEE",
    abstract = "In recent years, deep networks have led to dramatic improvements in speech enhancement by framing it as a data-driven pattern recognition problem. In many modern enhancement systems, large amounts of data are used to train a deep network to estimate masks for complex-valued short-time Fourier transforms (STFTs) to suppress noise and preserve speech. However, current masking approaches often neglect two important constraints: STFT consistency and mixture consistency. Without STFT consistency, the system's output is not necessarily the STFT of a time-domain signal, and without mixture consistency, the sum of the estimated sources does not necessarily equal the input mixture. Furthermore, the only previous approaches that apply mixture consistency use real-valued masks; mixture consistency has been ignored for complex-valued masks."
}

@unpublished{Turpault2020b,
    AUTHOR = "Turpault, Nicolas and Wisdom, Scott Wisdom and Erdogan, Hakan and Herhey, John R. and Serizel, Romain and Fonseca, Eduardo and Seetharaman, Prem",
    title = "Improving Sound Event Detection In Domestic Environments Using Sound Separation",
    note = "working paper or preprint",
    institution = "Universit{\'e} de Lorraine, CNRS, Inria, Loria, France",
    year = "2020",
    abstract = "Performing sound event detection on real-world recordings often implies dealing with overlapping target sound events and non-target sounds, also referred to as interference or noise. Until now these problems were mainly tackled at the classifier level. We propose to use sound separation as a pre-processing stage for sound event detection. In this paper we start from a sound separation model trained on the Free Universal Sound Separation dataset and the DCASE 2020 task 4 sound event detection baseline. We explore different methods of combining separated sound sources and the original mixture within the sound event detection. Furthermore, we investigate the impact of adapting the universal sound separation model to the sound event detection data in terms of both separation and sound event detection performance."
}

@inproceedings{Turpault2019_DCASE,
    Author = "Turpault, Nicolas and Serizel, Romain and Parag Shah, Ankit and Salamon, Justin",
    title = "{Sound event detection in domestic environments with weakly labeled data and soundscape synthesis}",
    booktitle = "{Workshop on Detection and Classification of Acoustic Scenes and Events}",
    address = "New York City, United States",
    year = "2019",
    month = "October",
    keywords = "Sound event detection ; Weakly labeled data ; Semi-supervised learning ; Synthetic data",
    abstract = "This paper presents Task 4 of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2019 challenge and provides a first analysis of the challenge results. The task is a followup to Task 4 of DCASE 2018, and involves training systems for large-scale detection of sound events using a combination of weakly labeled data, i.e. training labels without time boundaries, and strongly-labeled synthesized data. The paper introduces Domestic Environment Sound Event Detection (DESED) dataset mixing a part of last year dataset and an additional synthetic, strongly labeled, dataset provided this year that we’ll describe more in detail. We also report the performance of the submitted systems on the official evaluation (test) and development sets as well as several additional datasets. The best systems from this year outperform last year’s winning system by about 10\% points in terms of F-measure.",
    hal_id = "hal-02160855",
    hal_version = "v2",
    url = "https://hal.inria.fr/hal-02160855"
}

@inproceedings{Wisdom_InPrep2020,
    Author = "Wisdom, Scott and Erdogan, Hakan and Ellis, Daniel P. W. and Serizel, Romain and Turpault, Nicolas and Fonseca, Eduardo and Salamon, Justin and Seetharaman, Prem and Hershey, John R.",
    title = "What's All the FUSS About Free Universal Sound Separation Data?",
    year = "2020",
    booktitle = "in preparation"
}

@unpublished{Turpault2020a,
    AUTHOR = "Turpault, Nicolas and Serizel, Romain",
    title = "Training Sound Event Detection On A Heterogeneous Dataset",
    note = "working paper or preprint",
    institution = "Universit{\'e} de Lorraine, CNRS, Inria, Loria, France",
    year = "2020",
    abstract = "Training a sound event detection algorithm on a heterogeneous dataset including both recorded and synthetic soundscapes that can have various labeling granularity is a non-trivial task that can lead to systems requiring several technical choices. These technical choices are often passed from one system to another without being questioned. We propose to perform a detailed analysis of DCASE 2020 task 4 sound event detection baseline with regards to several aspects such as the type of data used for training, the parameters of the mean-teacher or the transformations applied while generating the synthetic soundscapes. Some of the parameters that are usually used as default to replicate other approaches are shown to be sub-optimal."
}

@inproceedings{Kavalerov_WASPAA2019,
    Author = "Kavalerov, Ilya and Wisdom, Scott and Erdogan, Hakan and Patton, Brian and Wilson, Kevin and {Le Roux}, Jonathan and Hershey, John R.",
    title = "Universal Sound Separation",
    year = "2019",
    booktitle = "{IEEE} Workshop on Applications of Signal Processing to Audio and Acoustics ({WASPAA})",
    month = "October",
    pages = "175--179",
    url = "https://arxiv.org/abs/1905.03330"
}

@inproceedings{Tzinis_ICASSP2020,
    Author = "Tzinis, Efthymios and Wisdom, Scott and Hershey, John R. and Jansen, Aren and Ellis, Daniel P. W.",
    title = "Improving Universal Sound Separation Using Sound Classification",
    year = "2020",
    booktitle = "{IEEE} International Conference on Acoustics, Speech, and Signal Processing ({ICASSP})",
    month = "May",
    url = "https://arxiv.org/abs/1911.07951"
}

@inproceedings{Wisdom_ICASSP2019,
    author = "Wisdom, Scott and Hershey, John R and Wilson, Kevin and Thorpe, Jeremy and Chinen, Michael and Patton, Brian and Saurous, Rif A",
    title = "Differentiable consistency constraints for improved deep speech enhancement",
    booktitle = "ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",
    pages = "900--904",
    year = "2019",
    organization = "IEEE",
    abstract = "In recent years, deep networks have led to dramatic improvements in speech enhancement by framing it as a data-driven pattern recognition problem. In many modern enhancement systems, large amounts of data are used to train a deep network to estimate masks for complex-valued short-time Fourier transforms (STFTs) to suppress noise and preserve speech. However, current masking approaches often neglect two important constraints: STFT consistency and mixture consistency. Without STFT consistency, the system's output is not necessarily the STFT of a time-domain signal, and without mixture consistency, the sum of the estimated sources does not necessarily equal the input mixture. Furthermore, the only previous approaches that apply mixture consistency use real-valued masks; mixture consistency has been ignored for complex-valued masks."
}

@unpublished{Turpault2020b,
    AUTHOR = "Turpault, Nicolas and Wisdom, Scott Wisdom and Erdogan, Hakan and Herhey, John R. and Serizel, Romain and Fonseca, Eduardo and Seetharaman, Prem",
    title = "Improving Sound Event Detection In Domestic Environments Using Sound Separation",
    note = "working paper or preprint",
    institution = "Universit{\'e} de Lorraine, CNRS, Inria, Loria, France",
    year = "2020",
    abstract = "Performing sound event detection on real-world recordings often implies dealing with overlapping target sound events and non-target sounds, also referred to as interference or noise. Until now these problems were mainly tackled at the classifier level. We propose to use sound separation as a pre-processing stage for sound event detection. In this paper we start from a sound separation model trained on the Free Universal Sound Separation dataset and the DCASE 2020 task 4 sound event detection baseline. We explore different methods of combining separated sound sources and the original mixture within the sound event detection. Furthermore, we investigate the impact of adapting the universal sound separation model to the sound event detection data in terms of both separation and sound event detection performance."
}